researchmm / soho

[CVPR'21 Oral] Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
206 stars 19 forks source link

The Accuracy of Masked Visual Modeling #10

Open mhyeh opened 3 years ago

mhyeh commented 3 years ago

Hi, what is your mvm accuracy of pretrained model? I only got about 30% when pretraining and wanted to know if that is normal?

IISCAditayTripathi commented 1 year ago

Any update on this ?